In this chapter, a method for distinguishing a pet, a human inside an intelligent environment/building equipped with a PIR sensor is proposed. Wavelet based features are extracted from PIR sensor outputs and are fed to two HMMs for human and pet. Sensor recordings containing various human and pet motions are used for training the HMMs corresponding to human and pet models. Clas-sification is done by the results of the probabilities of each HMMs. This sensor can be used as an assistant to a camera based system or can be complementary to a multitude sensor system [14]. The proposed system can further be improved to handle false alarm sources like barking dogs, wind, slamming doors and so forth. This can be achieved by training models similar to ones defined in this chapter. It can also be used to increase the robustness of camera-based systems inside and outside of an intelligent building.
Chapter 4
Flame Detection
In this chapter, a flame detection system based on wavelet analysis of PIR sensor signals is described. Since PIR sensor is sensitive to IR radiation, PIR sensor re-sponds to flames as well as it does to any other moving hot object. The problem is to find some special characteristics that belong to flames for separating them from other objects and these must be robust enough to have a low false alarm ratio.
Conventional point smoke and fire detectors typically detect the presence of certain particles generated by smoke and fire by ionization or photometry. An important weakness of point detectors is that the smoke has to reach the sensor.
This may take significant amount of time to produce an alarm and therefore it is not possible to use them in open spaces or large rooms. The main advantage of PIR based sensor system for fire detection over the conventional smoke detec-tors is the ability to monitor large rooms and spaces because they analyze the infrared light reflected from hot objects or fire flames to reach a decision. When we apply different algorithms on the same sensor it is possible to detect different events. So instead of using different type sensors, we can just use PIDs.
Moreover, there are also some disadvantages of the system over conventional smoke detectors. One of them occurs because of the complex layout of any room.
35
In order to get robust results, PIR sensor should directly see the flames. If the flame occurs behind a big object, the probability of detection decreases since the object masks the IR radiation. In addition, different PID sensors can give same characteristic signals for the same event but with different amplitudes. The reason is because of the differences of the structure. Even this, can be observed between same types of 2 PIDs. The algorithm should be calibrated for every sensor. Another disadvantage is the test case. We implement some tests for dif-ferent situations but more detailed tests should be applied for difdif-ferent ambient conditions with different situations in order to get more trustable and robust system.
It is reported that turbulent flames of an uncontrolled fire flicker with a fre-quency of around 10 Hz [16, 17]. Recently developed video based fire detection schemes also take advantage of this fact by detecting periodic high-frequency behavior in flame colored moving pixels [18] - [20]. Actually, instantaneous flame flicker frequency is not constant and it varies in time. As reported in [31] and [29], flame flicker behavior is a wide-band activity covering 1 Hz to 13 Hz. Therefore, a Markov model based modeling of flame flicker process produces more robust performance compared to frequency domain based methods. Markov models are extensively used in speech recognition systems and in computer vision applica-tions [21]-[24]. In [29], several experiments on the relaapplica-tionship between burner size and flame flicker frequency are presented. Recent research on pyro-IR based combustion monitoring includes [30] where monitoring system using an array of PIR detectors is realized.
A regular camera or typical IR flame sensors have a fire detection range of 30 meters. This is due to the fact that flicker in flames cannot be or sensed from longer distances. Therefore, PIR based systems provide a cost-effective solution to the fire detection problem in relatively large rooms as the unit cost of a camera based system or a regular IR sensor based system is in the order of one thousand dollars.
CHAPTER 4. FLAME DETECTION 37
We also used wavelet domain signal processing, which provides robustness against sensor signal drift due to temperature variations in the observed area.
Regular temperature changes due to hot plates and radiators are slow variations compared to the moving objects and flames. Since wavelet sub-signals of a wave-form are high-pass and band-pass in nature they do not get affected by the slow variations.
Events are classified into two different classes in this approach. The first class represents fire events, on the other hand, the second class represents non-fire events. Since PIR sensor circuits are designed for detecting the movement of hot objects, we include regular human motion events such as walking or running in the non-fire event class.
The PIR sensor can be considered as a single-pixel camera without loss of generality. Therefore, the proposed PIR based fire detection algorithm is ob-tained methods developed in Chapter 2.
Data acquisition and the PIR systems are described in the next Section. The proposed algorithm and the experiments are presented in Sections 4.2 and 4.3, respectively.
4.1 Data Acquisition
In order to get the digital samples from PID, digital sampling structure described in the first Chapter is used. In addition, for capturing the flame flicker process the analog signal is sampled with a sampling frequency of fs = 50 Hz because the highest flame flicker frequency is 13 Hz [17] and fs = 50 Hz is well above 2 × 13 Hz. In Figure 4.1, a frequency distribution plot corresponding to a flickering flame of an uncontrolled fire is shown. It is clear that the sampling frequency of 50 Hz is sufficient.
Typical sampled signal for no activity case using 8 bit quantization is shown in Figure 4.2.
Figure 4.1: Flame flicker spectrum distribution.
Figure 4.2: Background signal sampled with 50Hz.
Other typical received signals from a moving person, shaking hands and flick-ering fire are presented in Figures 4.3, 4.4 and 4.5.
CHAPTER 4. FLAME DETECTION 39
Figure 4.3: Walking man at 5 m.
Figure 4.4: Flame at 5 m.
Figure 4.5: Shaking hands at 1 m.
The strength of the received signal from a PIR sensor increases when there is motion due to a hot body within its viewing range. However, the motion may be due to human motion taking place in front of the sensors or flickering flame.
As can be noticed from the figures, shaking hands and flame flicker have a close behaviour. In this chapter the PIR sensor data is used to distinguish the flame flicker from the motion of a human being like running or walking. Typically the PIR signal frequency of oscillation for a flickering flame is higher than that of PIR signals caused by a moving hot body. In order to keep the computational cost of the detection mechanism low, we decided to use Lagrange filters for obtaining the wavelet transform coefficients as features instead of using a direct frequency approach, such as FFT based methods. On the other hand in the next section it is shown that wavelet results are more distinguisable compared to fft results.
CHAPTER 4. FLAME DETECTION 41